|Publication number||US6874147 B1|
|Application number||US 09/443,026|
|Publication date||Mar 29, 2005|
|Filing date||Nov 18, 1999|
|Priority date||Nov 18, 1999|
|Publication number||09443026, 443026, US 6874147 B1, US 6874147B1, US-B1-6874147, US6874147 B1, US6874147B1|
|Original Assignee||Intel Corporation|
|Export Citation||BiBTeX, EndNote, RefMan|
|Patent Citations (5), Non-Patent Citations (1), Referenced by (83), Classifications (15), Legal Events (5)|
|External Links: USPTO, USPTO Assignment, Espacenet|
The invention generally relates to networking, and more particularly to runtime manipulation of networking drivers.
Since the advent of computers, various techniques have been used to allow computers to communicate. The common term for such communication is “networking” and many different models have been developed to describe the communication process. A well-known approach to representing networking communication is through use of the Open Systems Interconnection (OSI) Reference Model, which is a seven-layer model put forth by the International Standards Organization (ISO) in 1983.
The seven layers are the physical, data link, network, transport, session, presentation, and application layers; each layer represents a successive level of complexity and data-abstraction for an underlying raw data stream. That is, the physical layer (part of a network interface card (NIC)) is generally responsible for transmitting and receiving raw data (bits) from a network medium or interface. The physical layer does not maintain or require any particular structure to the data. The data link layer, however, abstracts the raw data stream into a series of frames, or chunks of raw data, allowing this layer to be generally responsible for ensuring that data is correct (e.g., all data received is correct). The network layer concerns properly routing data to and from appropriate sources and destinations. Each remaining layer is similarly responsible for providing further abstraction and integrity to a data stream. (For further information regarding the OSI model, see Computer Networks by Andrew Tanenbaum, Prentice Hall (2d. Ed. 1989).)
In order to distinguish one NIC from another, the NICs each have a unique identifier, commonly referred to as a Media Access Control (MAC) identifier. Communication protocols are bound to one or more NICs, allowing data utilizing the protocol to be routed over bound NICs. Commonly used protocols include connection-oriented protocols such as Transmission Control Protocol (TCP) and Sequenced Packet Exchange (SPX), as well as connectionless protocols such as Internet Protocol (IP), Internetwork Packet Exchange (IPX), and User Datagram Protocol (UDP).
Binding a NIC with a protocol is normally an operating-system boot-time event. For networking, after a machine performs its power-on self test (POST), and the operating system begins to load, control is passed to networking drivers which bind an instance of themselves to each NIC, and to one or more protocol stacks. The drivers also request its associated NIC to provide the NIC's MAC address. This address is stored in a memory reserved for the driver, and is also stored in the NIC's receive address filtering hardware. Once all NIC drivers have been initialized, data can be routed to and from each NIC.
Unfortunately, as will become clear in the following detailed description, once the Protocol stacks are bound to NICs using their drivers, there is no way to handle a NIC failure. If a particular NIC is used in a communication session between a source and a destination computer, and the NIC fails, current networking software does not allow silent replacement of the failed NIC with an operative NIC. Instead, a communication error occurs, preventing the application programs from being able to continue communication.
Some attempts have been made to overcome NIC failure issue. One solution is to overcome NIC failure by using standard functions to identify routing changes. If a NIC changes, a broadcast of a routing change is made to all clients, indicating that they need to switch to a new destination address (e.g., the replacement NIC). This solution, however, lacks transparency. Another alternate, as discussed in U.S. Pat. No. 5,661,719, is to provide NICs with programmable MAC addresses. This allows a new NIC to emulate the failed NIC, but it is a solution lacking flexibility.
One aspect of the invention is an application programming interface (API) for enhancing data network communication. The API includes an identify address function including programming instructions for identifying a stored node address stored by a base driver for a network interface associated with the base driver. The API also includes an update node address function including programming instructions for directing the base driver to update the stored node address with a new node address in a configuration storage of the base driver, and in a receive address filtering table for the network interface.
Features and advantages of the invention will become apparent to one skilled in the art to which the invention pertains from review of the following detailed description and claimed embodiments of the invention, in conjunction with the drawings in which:
In the illustrated configuration, the intermediary 102 appears to the stack 100 as a multiplexer to the different base drivers. The stack and base drivers are bound to the intermediary, resulting in network data received by the protocol stack being routed to the intermediary. The intermediary then becomes responsible for forwarding the network data on to an appropriate base driver 104-108 which is then responsible for transfer of the data to the NIC hardware 116-120 for delivery over a network connection 122.
On data reception over the network 122, all NICs see the data, but only the NIC hardware with the appropriate matching MAC filter responds to the incoming data. If a NIC accepts network data, it is forwarded to its driver, which in turn forwards it to the intermediary layer which multiplexes the data to an appropriate protocol stack.
The intermediary layer is capable of accepting many upper-layer protocol stacks, in addition to multiple drivers below it. Although not provided by present networking environments, this ability provides an opportunity for allowing transparent fail-over, load-balancing, and support for new network protocols and features, without changing existing base drivers 104-108 for current network interfaces 116-120.
In order to present a concrete example of how the intermediary layer 102 can be used to transparently extend the capabilities of existing network configurations, it will be assumed that a standard Novell Open Data-link Interface (ODI) based network is being extended. The ODI environment is a well known network configuration which does not provide for transparent logical replacement of a failed or failing NIC, nor support for features not natively supported by NIC networking software (e.g., the NIC drivers 104-108). It will be clear to one skilled in the art how to implement the invention in other network environments, e.g., Windows 9×/NT, Macintosh, Unix/Linux, etc., as each environment uses an intermediary layer.
Shown are the seven OSI layers 204-218, and the corresponding ODI layers 220-226 that are different from the OSI model. The protocol stack (PS) 220 represents each protocol implementation (e.g., SPX, AppleTalk, etc.) available within a computer.
The Multiple Link Interface Drivers (MLIDs) 224 are device drivers which send and receive packets to and from the physical layer (or logical topology) 218, 226. MLIDs have three portions, a Media Support Module (MSM), a Topology Specific Module (TSM), and a Hardware Specific Module (HSM). The HSM portion of MLIDs append or strip frame headers from data received over the physical layer, but they do not interpret packet data. Instead, received packets are passed on to the TSM and MSM for packet type classifying and then forwarded to Link Support Layer (LSL) 220 to be multiplexed to the appropriate protocol stack based on the contents of Event Control Blocks (ECBs).
ECBs are NetWare buffers that are used to send, receive and manage packet data. Generally an ECB contains information set by a protocol containing a block (e.g., 1500 bytes) of data. Such information includes the protocol originating the data, the NIC to which the data is to be sent, context information for the data, as well as other housekeeping information maintained by the protocol. The LSL effectively operates as a router, and coordinates communication between protocol stacks and MLIDs.
Traditionally, when data is transmitted, a protocol stack 220 receives data from an application program 204. The PS 220 determines whether to split the data into fragments, and also determines the size of the fragments. The PS adds a protocol header to the data, destination MAC address and logical board through which packet will be transmitted are placed in the ECB, and sends the data to the LSL 222. The LSL routes the data to an appropriate MLID 224. The MLID adds a MAC header to the data, and hands the data to the appropriate NIC (LAN adapter). Recall that the source MAC address added to the MAC header was read from the NIC during network initializabon; this value is retained by the MLID for later use. (It is too time consuming to query each NIC for its MAC address each time data needed is transmitted or received—hence this determination is supposed to be only performed once.) NIC 226 adds a packet preamble and places the data on the wire (alternatively, the medium may be wireless).
Receipt of transmitted data operates conversely. On data receipt, the NIC strips the packet preamble from received data. Only packets which meet the NIC's stored MAC address passes the NIC's receive filter. The MLID strips the MAC header from the data, places various fields in an ECB and forwards the data pointed by the ECB to the LSL. The LSL routes the packet to the appropriate PS, and the PS removes the protocol header and transfers the data to the application.
Unfortunately, as noted above, in a traditional communication model, transmission and receipt breaks down if the NIC fails. Failure can happen by hardware failure, disconnected cable, or other communication breakdown. That is, since the data stream is hard-wired to travel to a particular NIC, a failed NIC will cause communication to fail.
In a traditional communication configuration, the LSL routes communication data to MLIDs 308-310 according to MLID identifiers (usually a logical board number) embedded within such communication which correspond to stored within the PS, the LSL and the MLID for corresponding. Instead, here, the protocol stack 300 is bound to the virtual MLID 306. Other protocols can be similarly bound. The virtual MLID appears to the LSL as a real adapter card's MLID driver. Consequently, network data 320 originating from the protocol stack 300 is routed by the LSL 302 to the virtual MLID 306 as normal. As discussed above with respect to
This configuration allows the data 320 to be repackaged in a protocol format entirely different from the original protocol's format. Recall that the underlying philosophy to the OSI 200/ODI 202 models is that each higher layer provides extra functionality and/or features to a communication stream, such as data integrity checks, reliability checks, out-of-order packet re-ordering, etc. Thus, the virtual protocol may retransmit the data 320 in a specialized encryption format (e.g., IPsec), or in a virtual LAN format, or other format. (See also
Further, the repackaged data can be addressed so that it is directed towards any of the MLIDs 308-312, allowing dynamic alteration of which MLID will be used for communication. The virtual MLID maintains a correspondence between originating protocol stack 300 for a particular data stream 320, and the MLID 310 to which the data stream was delivered. When a transmit response is received by MLID 310, the LSL 302 routes the response back to the “originating PS”, i.e., virtual PS 304. Internally, this response is stripped off any additional protocol features added to the outgoing data stream, and is presented back to the LSL 302 as if just received by the virtual MLID 306. The LSL then routes this response back to the real originating protocol stack 300, with the protocol stack 300 and LSL 302 being unaware of the data indirection.
One method for effecting the data repackaging is to copy and modify ECBs. In Novell networking, each transmitted data stream includes an Event Control Block (ECB) along with pointers to an ECB data payload (pointers within the ECB point to data buffers containing the payload). While redirecting the data 320, the ECB for this data is copied into a second ECB (per networking conventions, the first ECB should not be modified). The second ECB's payload pointers (e.g., FragmentOffset, FragmentSize) remain directed at the first ECB's payload data buffers. To track the copy, the second ECB is adjusted to back-reference the original ECB. This can be accomplished through an entry in the copied ECB's ProtocolWorkspace portion. This second ECB is also adjusted to direct the data towards a MLID of interest. Similar header copying and adjustment may be used for other networking environments (e.g., Linux/Unix, Macintosh, Microsoft Windows 9×/NT, etc.). By creating copies of the ECBs, one can control the format and destination of data originally received from the protocol stack 300.
Shown is a control line 322 (e.g., data pathway) in communication with each MLID 308-312. The control line 322 can be implemented using the Driver Management Input/Output Control (IOCTL) method defined in ODI Lan Driver specification, where a formatted management ECB is sent to a base driver. A command/query communication data structure can be defined using a standard NetWare ECB buffer used in the Novell driver management API. This command/query ECB will be filled with appropriate command and related parameters, and then be handed to an MLID base driver by calling the Ctl14_DriverManagement API. The base driver will act according to the command field in this buffer and fill a response result and parameters in the same buffer. In particular, an MLID can be directed to replace its stored MAC address with a different value, thus replacing the value obtained when initializing the networking hardware 330-334 and software (usually occurring at base driver load time). The MLID stores the new MAC address in the NIC's address filtering hardware as well as in the MLID's configuration table. Another care is taken to update the TSM's source MAC address field it adds to every transmitted packet, with the new updated MAC address.
Once a MLID can be instructed to revise its stored MAC address, multiple NICs can be installed in a machine, but where only one NIC 332 is actively communicating through its MLID 310, and the others 308/330, 312/334 are left “disabled” for fail-over purposes. In one embodiment, an Adapter Fault Tolerance (AFT) mode is provided, where a fail over NIC waits for failure of an active NIC. (See also
Similarly, in one embodiment, load balancing may be effected by directing plural MLIDs 308-312 to store an identical MAC address. The virtual PS 304 can then monitor data traffic flow to identify a least-busy NIC and direct the LSL 302 to route data 320 to that NIC. (The LSL does not route data to MLIDs based on the stored MAC address.) In this embodiment, an Adaptive Load Balancing (ALB) mode, and Link Aggregation mode is provided, where all NICs are active, until one fails, causing the failed NIC to be removed from load balancing until it is repaired.
Each NIC 330-334, unaware of the MAC address stored in its associated MLID driver, receives the data stamped in the source address field by its MLID with the stored MAC address and submits it to the wire 336 for delivery.
Upon receipt of end of transmit response, the NIC presents the response to its MLID. The MLID passes the response to the LSL which routes it back to the virtual PS 304. Recall that the virtual PS 304 and MLID 306 have maintained a concordance between data received from an originating protocol stack 300 and the MLID to which the data was ultimately forwarded. Based on this, the data can be returned to the originating protocol stack 300.
The identified 408 secondary NIC is set 410 to utilize the MAC for the failed primary NIC. When asynchronously polling NICs, replacement of the failed NIC occurs before a sender of data receives a time out or other communication error from attempting communication through the failed NIC. In an alternate embodiment, NIC testing is performed along with data transmission, such that the base driver is polled 402 and evaluated 404 before data transferred 406 to a NIC.
Note that in an alternate embodiment, testing 402 a NIC, identifying 404 its health, and selecting a fail over NIC 408, 410 can be performed asynchronously (e.g., in parallel) to regular network traffic processing. In this alternate embodiment, data is received 400 and processing continues directly with checking 412 whether a new protocol of feature is being used. A database, run-time variable, or other memory is used to store a MAC (or other identifier) address for a current primary adapter (e.g., the NIC presently in-use) to be used for network transfers. In parallel to processing received data, a separate process performs the testing 402, 404 and fail-over selection 408, 410 of a replacement NIC.
In an API configuration, the control interface 322 is based on a master slave protocol, where the virtual PS 304 and MLID 306 are the master, and the base drivers 308-312 are the slave. The slave drivers are polled at a predetermined polling period, e.g., 100 to 400 milliseconds or other period depending on data response requirements. As an alternative to polling, one can generate events from a base driver through the Novell Event Bus (NEB), with the virtual PS and MLID registered to receive events. However, for simplicity in presentation, it has been assumed that polling is utilized, and that the MLID base drivers respond to control messages immediately.
In response to the identity check, the base driver should return the following fields: CommRevision 503, which indicates the driver's communication interface revision number; VendorID 504, which indicates a vendor ID value of base driver; ResponseCode 506, which embodies a response, if any, to commands sent to the base driver; and CopyrightString 508, a protected statement returned by a driver to indicate that the driver is authorized to be communicating with the virtual PS. For example, to ensure that only licensed vendors are using the virtual PS to repackage network communication in a new (e.g., previously unsupported) format, the driver can be required to return a copyrighted string before the virtual PS will communicate with that driver. Since the string is protected under copyright (and other applicable regulations), to be compatible with the virtual PS environment, one would have to seek proper authorization, or illicitly use the string. In this latter context, such illicit use may subject one to significant liability.
Another API command is ReportNodeAddress 510. This command is used to identify a base drivers stored MAC address. As discussed above, this value can be determined by returned value from the driver. Or, alternatively, the address can be determined by inspecting the configuration table of the driver.
Another API command is UpdateNodeAddress 512. This command is used to tell a driver to override its MAC address with a new MAC address 513 passed as a calling parameter. As discussed above, this command can be used at fail over time for fault tolerance, or when load balancing (e.g., link aggregation mode for aggregated bandwidth) where all underlying NICs use the same MAC address. As a result of this command, a base driver should update its MAC address in its configuration table, MSM (under Novell) shared data space, and in its hardware receive filtering table. If the driver (or its NIC) is not ECB aware, then the new address should be written on every packet the base driver delivers to the NIC (e.g., in the DriverSend routine). Writing the new address overcomes a limitation in the ODI specification and the way MSM and EtherTSM are implemented.
Note that fail over can be used to allow uninterrupted network communication during hot plug removal of a NIC, such as in a PCI environment. When a card is removed, the base driver will report (in response to the ReportStatus request) the removed card. If card was the primary adapter (e.g., in use), network communication will fail over to a secondary adapter with the secondary NIC getting the MAC address of the primary adapter. If it is desirable to maintain separate MAC addresses when the removed card is returned, the primary and secondary cards can be instructed to swap MAC addresses. The driver representing the card in hot plug event will be called to update its MAC address even though the NIC is not present. When the card is reinserted, the driver should use the swapped address. This function can also be used in fail over conditions during Adaptive Load Balancing (ALB) (ALB balances outgoing server traffic among multiple NICs, providing scalable bandwidth as well as automatic backup links through fault tolerance).
Another API command is ReportStatus 514. This command is used to ask a base driver to report its running status. In response, a base driver can report operating conditions such as link change 516, line speed 518, duplex 520, hardware failure condition 522, hot plug PCI event (card removal) 524 or other results as desired. As discussed above, status will be polled at a predetermined interval (e.g., 100-400 400 msec) according to required response times.
Continuing on to
Another API command is ReportVlanCapabilities 534. If virtual LAN support is present, this command can be used to ask a base driver to report what VLAN standards 536 it supports, whether VLAN mode can be enabled or disabled 538, and whether the base driver supports VLAN RX filtering 540 (this support, if performed in hardware, will offload from a system's PCI bus any VLAN traffic not destined for the system).
Another API command is VLanControl 542. This command is used to ask a base driver to change VLAN modes 544, if changing modes is supported (depends on the supported standards 536), or to set the VLAN filtering mode (if supported).
Another API command is SetControl 546. This command is used to ask a base driver to revise basic functionality. This is an opened function and depends on functionality required of the base driver and/or NIC. This command can be used, for example, to enable or disable ECB out of band mode 548. (At unbind time, original driver settings will be restored.)
Another API command is BD_Disconnect 550. This command notifies a base driver that this new advanced contol communication with the driver has been terminated. This provides opportunity for the driver to recover, if necessary, or make adjustments due to the termination of communication.
FIG. 7 and the following discussion are intended to provide a brief, general description of a suitable computing environment in which the claimed invention may be practiced. The invention may be described by reference to different high-level program modules and/or low-level hardware contexts. Those skilled in the art will realize that program module references can be interchanged with low-level hardware instructions.
Program modules include procedures, functions, programs, components, data structures, and the like, that perform particular tasks or implement particular abstract data types. The modules may be incorporated into single and multi-processor computing systems, as well as hand-held devices and controllable consumer devices. It is understood that modules may be implemented on a single computing device, or processed over a distributed network environment, where modules can be located in both local and remote memory storage devices.
An exemplary system for implementing the invention includes a computing device 602 having system bus 604 for coupling together various components within the computing device. The system bus 604 may be any of several types of bus structure including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of conventional bus architectures such as PCI, AGP, VESA, Microchannel, ISA and EISA, to name a few. Note that only a single bus is illustrated, although plural buses typically achieve performance benefits. Typically, attached to the bus 602 are at least one processor 606, memory 608, storage device (e.g., fixed 610, removable 612, optical/laser 614), video interface 616, input/output interface port 618, and network interface 620.
The processor 606 may be any of various commercially available processors, including Intel processors, or the DEC Alpha, PowerPC, programmable gate arrays, signal processors, or the like. Dual, quad processors, and other multi-processor architectures also can be used. The system memory includes random access memory (RAM) 622, and static or re-programmable read only memory (ROM) 624. A basic input/output system (BIOS), stored in ROM, flash ROM, cached to RAM or the like, contains routines for information transfer between device 602 components or device initialization.
The fixed storage 610 generally refers to hard drive and other semi-permanently attached media, whereas removable storage 612 generally refers to a device-bay into which removable media such as a floppy diskette is removably inserted. The optical/laser storage 614 include devices based on CD-ROM, DVD, or CD-RW technology, and are usually coupled to the system bus 604 through a device interface 626, 628, 630. The storage systems and associated computer-readable media provide storage of data and executable instructions for the computing device 602. Note that other storage options include magnetic cassettes, tapes, flash memory cards, memory sticks, digital video disks, and the like.
The exemplary computing device 602 can store and execute a number of program modules within the RAM 622, ROM 624, and storage devices 610, 612, 614. Typical program modules include an operating system 632, application programs 634 (e.g., a web browser or network application program), etc., and application data 636. Program module or other system output can be processed by the video system 616 (e.g., a 2D and/or 3D graphics rendering device), which is coupled to the system bus 604 and an output device 638. Typical output devices include monitors, flat-panels displays, liquid-crystal displays, and recording devices such as video-cassette recorders.
A user of the computing device 602 is typically a person interacting with the computing device through manipulation of an input device 640. Common input devices include a keyboard, mouse, tablet, touch-sensitive surface, digital pen, joystick, microphone, game pad, satellite dish, etc. One can also provide input through manipulation of a virtual reality environment, or through processing the output from a data file or another computing device.
The computing device 602 is expected to operate in a networked environment using logical connections to one or more remote computing devices. One such remote computing device 642 may be a web server or other program module utilizing a network application protocol (e.g., HTTP, File Transfer Protocol (FTP), Gopher, Wide Area Information Server (WAIS)), a router, a peer device or other common network node, and typically includes many or all of the elements discussed for the computing device 602. To provide NIC fail over, the computing device 602 has plural network interfaces 620 (e.g., an Ethernet card) as described above, having updateable MAC address. These interfaces 620 are coupled to the system bus 604, allowing communication with the remote device 642. Both the local computing device 602 and the remote computing device 642 can be communicatively coupled to a network 644 such as a WAN, LAN, Gateway, Internet, or other public or private data-pathway. It will be appreciated that other communication links between the computing devices, such as through a modem 646 coupled to an interface port 618, may also be used.
In accordance with the practices of persons skilled in the art of computer hardware and software programming, the present invention is described with reference to acts and symbolic representations of operations that are sometimes referred to as being computer-executed. It will be appreciated that the acts and symbolically represented operations include the manipulation by the processor 606 of electrical signals representing data bits which causes a resulting transformation or reduction of the electrical signal representation, and the maintenance of data bits at memory locations in the memory 608 and storage systems 610, 612, 614, so as to reconfigure or otherwise alter the computer system's operation and/or processing of signals. The memory locations where data bits are maintained are physical locations having particular electrical, magnetic, or optical properties corresponding to the data bits.
Having described and illustrated the principles of the invention with reference to illustrated embodiments, it will be recognized that the illustrated embodiments can be modified in arrangement and detail without departing from such principles. For example, while the foregoing description focused—for expository convenience—on the Novell networking/ODI API environment, it will be recognized that the same techniques and analyses can be applied to different networking configurations, such as certain Macintosh, Microsoft (NTx Win9x and the like) and Unix environments. In addition, even though description or claim language may speak to only one or two network interfaces, it will be appreciated that the invention is applicable to devices simultaneously utilizing many network interfaces.
And, even though the foregoing discussion has focused on particular embodiments, it is understood that other configurations are contemplated. In particular, even though the expressions “in one embodiment” or “in another embodiment” are used herein, these phrases are meant to generally reference embodiment possibilities, and are not intended to limit the invention to those particular embodiment configurations. These terms may reference the same or different embodiments, and unless indicated otherwise, are combinable into aggregate embodiments.
Consequently, in view of the wide variety of possible networking environments, the detailed embodiments are intended to be illustrative only, and should not be taken as limiting the scope of the invention. Rather, what is claimed as the invention, is all such modifications as may come within the scope and spirit of the following claims and equivalents thereto.
|Cited Patent||Filing date||Publication date||Applicant||Title|
|US6131163||Feb 17, 1998||Oct 10, 2000||Cisco Technology, Inc.||Network gateway mechanism having a protocol stack proxy|
|US6253334||Oct 1, 1997||Jun 26, 2001||Micron Electronics, Inc.||Three bus server architecture with a legacy PCI bus and mirrored I/O PCI buses|
|US6279029||Oct 12, 1993||Aug 21, 2001||Intel Corporation||Server/client architecture and method for multicasting on a computer network|
|US6308282 *||Nov 10, 1998||Oct 23, 2001||Honeywell International Inc.||Apparatus and methods for providing fault tolerance of networks and network interface cards|
|US6381218||Sep 11, 1998||Apr 30, 2002||Compaq Computer Corporation||Network controller system that uses directed heartbeat packets|
|1||Fu et al "The Design of a Low Cost Local Area Network Using Netware" Sep. 1997 pp. 40-43.|
|Citing Patent||Filing date||Publication date||Applicant||Title|
|US7076787||May 30, 2002||Jul 11, 2006||Sun Microsystems, Inc.||Supporting multiple protocols with a single device driver|
|US7127601||May 30, 2002||Oct 24, 2006||Sun Microsystems, Inc.||System and method for delivering FPGA programming|
|US7197545 *||Apr 30, 2001||Mar 27, 2007||Sanavigator, Inc.||Techniques for dynamically loading modules for devices discovered in a storage network|
|US7318095 *||Oct 21, 2002||Jan 8, 2008||Clearcube Technology, Inc.||Data fail-over for a multi-computer system|
|US7389332||Apr 11, 2002||Jun 17, 2008||Cisco Technology, Inc.||Method and apparatus for supporting communications between nodes operating in a master-slave configuration|
|US7421478||Mar 7, 2002||Sep 2, 2008||Cisco Technology, Inc.||Method and apparatus for exchanging heartbeat messages and configuration information between nodes operating in a master-slave configuration|
|US7421615 *||Sep 27, 2004||Sep 2, 2008||Dell Products L.P.||Apparatus, method and system for selectively coupling a LAN controller to a platform management controller|
|US7451208 *||Jun 28, 2003||Nov 11, 2008||Cisco Technology, Inc.||Systems and methods for network address failover|
|US7474655 *||Jul 6, 2005||Jan 6, 2009||International Business Machines Corporation||Restricting communication service|
|US7506063 *||Aug 31, 2006||Mar 17, 2009||Noatak Software Llc||Method and system for initiating execution of software in response to a state|
|US7512686||Jun 1, 2001||Mar 31, 2009||Berg Mitchell T||Method and system for establishing a data structure of a connection with a client|
|US7546369||Jun 1, 2001||Jun 9, 2009||Berg Mitchell T||Method and system for communicating a request packet in response to a state|
|US7587465||Apr 22, 2002||Sep 8, 2009||Cisco Technology, Inc.||Method and apparatus for configuring nodes as masters or slaves|
|US7600004 *||Dec 20, 2004||Oct 6, 2009||Mitac Technology Corp.||Network setting configuration systems and methods|
|US7649876||Aug 31, 2006||Jan 19, 2010||Berg Mitchell T||Method and system for communicating an information packet through multiple router devices|
|US7668923 *||Oct 14, 2003||Feb 23, 2010||International Business Machines Corporation||Master-slave adapter|
|US7725932||Sep 5, 2008||May 25, 2010||International Business Machines Corporation||Restricting communication service|
|US7730210||Aug 15, 2008||Jun 1, 2010||Cisco Technology, Inc.||Virtual MAC address system and method|
|US7783784 *||Aug 31, 2004||Aug 24, 2010||Oracle America, Inc.||Method and apparatus for adaptive selection of algorithms to load and spread traffic on an aggregation of network interface cards|
|US7840706 *||Nov 30, 2007||Nov 23, 2010||Nvidia Corporation||Wake-on-LAN design in a load balanced environment|
|US7856480||May 15, 2007||Dec 21, 2010||Cisco Technology, Inc.||Method and apparatus for exchanging heartbeat messages and configuration information between nodes operating in a master-slave configuration|
|US7881289 *||Dec 22, 2004||Feb 1, 2011||At&T Intellectual Property Ii, L.P.||Method and apparatus for porting telephone numbers of endpoint devices|
|US8068498 *||Sep 21, 2005||Nov 29, 2011||Fujitsu Limited||Computer readable record medium on which data communication load distribution control program is recorded and data load distribution control method|
|US8233380 *||Nov 6, 2006||Jul 31, 2012||Hewlett-Packard Development Company, L.P.||RDMA QP simplex switchless connection|
|US8244916 *||Feb 14, 2002||Aug 14, 2012||Marvell International Ltd.||Method and apparatus for enabling a network interface to support multiple networks|
|US8295290 *||Sep 3, 2009||Oct 23, 2012||International Business Machines Corporation||Energy efficient control of data link groups|
|US8341290||Aug 31, 2006||Dec 25, 2012||Noatak Software Llc||Method and system for selecting a computing device for maintaining a client session in response to a request packet|
|US8369208 *||Sep 16, 2010||Feb 5, 2013||Microsoft Corporation||Fault-tolerant communications in routed networks|
|US8447887||Aug 13, 2012||May 21, 2013||Marvell International Ltd.||Method and apparatus for enabling a network interface to support multiple networks|
|US8542574 *||Jun 29, 2005||Sep 24, 2013||Honeywell International Inc.||Apparatus and method for network error prevention|
|US8582570||Feb 4, 2013||Nov 12, 2013||Tri-County Excelsior Foundation||Automatic attachment and detachment for hub and peripheral devices|
|US8582571||Feb 8, 2013||Nov 12, 2013||Tri-County Excelsior Foundation||Personal area network apparatus|
|US8588196||Mar 7, 2013||Nov 19, 2013||Tri-County Excelsior Foundation||Automatic attachment and detachment for hub and peripheral devices|
|US8588231||Mar 7, 2013||Nov 19, 2013||Tri-County Excelsior Foundation||Personal area network apparatus|
|US8675590||Mar 26, 2012||Mar 18, 2014||Tri-County Excelsior Foundation||Personal area network with automatic attachment and detachment|
|US8724465||Oct 28, 2009||May 13, 2014||International Business Machines Corporation||Zero packet loss energy efficient ethernet link transition via driver fast failover|
|US8862998||May 15, 2007||Oct 14, 2014||Brocade Communications Systems, Inc.||Method and system for generating a network monitoring display with animated utilization information|
|US8867376 *||May 4, 2012||Oct 21, 2014||Google Inc.||Host verification at an optical circuit switch|
|US8886839||May 15, 2013||Nov 11, 2014||Marvell International Ltd.||Method and apparatus for enabling a network interface to support multiple networks|
|US8892758||Oct 19, 2010||Nov 18, 2014||Microsoft Corporation||Plug and play device redirection for remote systems|
|US8918530 *||Apr 3, 2006||Dec 23, 2014||Microsoft Corporation||Plug and play device redirection for remote systems|
|US8958325 *||Jul 2, 2012||Feb 17, 2015||Microsoft Corporation||Fault-tolerant communications in routed networks|
|US9071499 *||Feb 13, 2012||Jun 30, 2015||Citrix Systems, Inc.||Systems and methods for emulating a NIC for packet transmission on hardware RSS unaware NICs in a multi-core system|
|US9100409||Nov 12, 2012||Aug 4, 2015||Noatak Software Llc||Method and system for selecting a computing device for maintaining a client session in response to a request packet|
|US9160771||Aug 13, 2013||Oct 13, 2015||International Business Machines Corporation||Method and apparatus for dynamic destination address control in a computer network|
|US9253293||Dec 30, 2014||Feb 2, 2016||Microsoft Technology Licensing, Llc||Fault-tolerant communications in routed networks|
|US20030112781 *||Dec 17, 2001||Jun 19, 2003||Kermode Roger George||Communications unit for secure communications|
|US20030120772 *||Oct 21, 2002||Jun 26, 2003||Husain Syed Mohammad Amir||Data fail-over for a multi-computer system|
|US20030204593 *||Apr 25, 2002||Oct 30, 2003||International Business Machines Corporation||System and method for dynamically altering connections in a data processing network|
|US20030225916 *||May 30, 2002||Dec 4, 2003||David Cheon||Implementing a data link layer protocol for multiple network interface devices|
|US20030225931 *||May 30, 2002||Dec 4, 2003||David Cheon||Supporting multiple protocols with a single device driver|
|US20030225942 *||May 30, 2002||Dec 4, 2003||David Cheon||System and method for delivering FPGA programming|
|US20040073640 *||Sep 23, 2002||Apr 15, 2004||Cricket Technologies Llc||Network load management apparatus, system, method, and electronically stored computer product|
|US20050068888 *||Sep 26, 2003||Mar 31, 2005||Komarla Eshwari P.||Seamless balde failover in platform firmware|
|US20050080933 *||Oct 14, 2003||Apr 14, 2005||International Business Machines Corporation||Master-slave adapter|
|US20060013224 *||Sep 21, 2005||Jan 19, 2006||Fujitsu Limited||Computer readable record medium on which data communication load distribution control program is recorded and data load distribution control method|
|US20060028993 *||Sep 27, 2004||Feb 9, 2006||Dell Products L.P.||Apparatus, method and system for selectively coupling a LAN controller to a platform management controller|
|US20060059552 *||Jul 6, 2005||Mar 16, 2006||Kentaro Aoki||Restricting communication service|
|US20060085540 *||Oct 18, 2004||Apr 20, 2006||Dell Products L.P.||System and method for the use of redundant network interface cards|
|US20060090012 *||Oct 22, 2004||Apr 27, 2006||Linden Cornett||Modular SDD (scalable device driver) framework|
|US20060136594 *||Dec 20, 2004||Jun 22, 2006||Mitac Technology Corp.||Network setting configuration systems and methods|
|US20060184813 *||Apr 13, 2006||Aug 17, 2006||Broadcom Corporation, A California Corporation||Wake on LAN power management|
|US20060209680 *||Mar 16, 2005||Sep 21, 2006||Chun-Liang Lee||Network link backup system|
|US20060245358 *||Apr 29, 2005||Nov 2, 2006||Beverly Harlan T||Acceleration of data packet transmission|
|US20060282840 *||May 25, 2005||Dec 14, 2006||Stone Peter S||Dynamic mapping of shared libraries|
|US20070002756 *||Jun 29, 2005||Jan 4, 2007||Honeywell International Inc.||Apparatus and method for network error prevention|
|US20070061418 *||Aug 31, 2006||Mar 15, 2007||Berg Mitchell T||Method and system for initiating execution of software in response to a state|
|US20070061477 *||Apr 3, 2006||Mar 15, 2007||Microsoft Corporation||Plug And Play Device Redirection For Remote Systems|
|US20070067046 *||Aug 28, 2006||Mar 22, 2007||Berg Mitchell T||Method and system for communicating an information packet through multiple networks|
|US20070214412 *||May 15, 2007||Sep 13, 2007||Sanavigator, Inc.||Method and System for Generating a Network Monitoring Display with Animated Utilization Information|
|US20070291704 *||Jun 14, 2006||Dec 20, 2007||Inventec Corporation||Internet protocol address take-over system in a local area network and method thereof|
|US20080034249 *||Aug 22, 2007||Feb 7, 2008||Husain Syed M A||Fail-Over In A Multi-Computer System|
|US20080126509 *||Nov 6, 2006||May 29, 2008||Viswanath Subramanian||Rdma qp simplex switchless connection|
|US20080285469 *||Oct 25, 2007||Nov 20, 2008||Masaru Toda||Computer replacing redundant communication routes, and programs and method for the same|
|US20080288607 *||May 15, 2007||Nov 20, 2008||Cisco Technology, Inc.||Method and apparatus for exchanging heartbeat messages and configuration information between nodes operating in a master-slave configuration|
|US20090007254 *||Sep 5, 2008||Jan 1, 2009||International Business Machines Corporation||Restricting communication service|
|US20090049199 *||Aug 15, 2008||Feb 19, 2009||Cisco Technology, Inc.||Virtual mac address system and method|
|US20110004783 *||Sep 16, 2010||Jan 6, 2011||Microsoft Corporation||Fault-tolerant communications in routed networks|
|US20110035758 *||Oct 19, 2010||Feb 10, 2011||Microsoft Corporation||Plug and play device redirection for remote systems|
|US20110051734 *||Sep 3, 2009||Mar 3, 2011||International Business Machines Corporation||Energy efficient control of data link groups|
|US20110096659 *||Oct 28, 2009||Apr 28, 2011||International Business Machines Corporation||Zero Packet Loss Energy Efficient Ethernet Link Transition Via Driver Fast Failover|
|US20120253780 *||Feb 13, 2012||Oct 4, 2012||Ramanjaneyulu Talla||Systems and methods for emulating a nic for packet transmission on hardware rss unaware nics in a multi-core system|
|US20120272093 *||Jul 2, 2012||Oct 25, 2012||Microsoft Corporation||Fault-tolerant communications in routed networks|
|U.S. Classification||719/328, 370/216, 714/1, 709/220|
|International Classification||H04L29/12, G06F9/46, H04L29/14|
|Cooperative Classification||H04L69/40, H04L29/12839, H04L29/12009, H04L61/6022|
|European Classification||H04L61/60D11, H04L29/14, H04L29/12A, H04L29/12A9D11|
|Feb 23, 2000||AS||Assignment|
Owner name: INTEL CORPORATION, CALIFORNIA
Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:DIAMANT, NIMROD;REEL/FRAME:010629/0565
Effective date: 20000203
|May 31, 2005||CC||Certificate of correction|
|Sep 22, 2008||FPAY||Fee payment|
Year of fee payment: 4
|Sep 26, 2012||FPAY||Fee payment|
Year of fee payment: 8
|Nov 4, 2016||REMI||Maintenance fee reminder mailed|